Pub Date : 2021-09-19DOI: 10.1109/ICIPC53495.2021.9620178
Shubham Chaudhary, Parima Jain, V. Jakhetiya, Sharath Chandra Guntuku, B. Subudhi
In this work, we propose a localization and masking-based satellite and debris classification technique. SPAce-craft Recognition leveraging Knowledge of space environment (SPARK) dataset consists of 120K images where both RGB and corresponding Depth images are available. However, the depth images are noisy and inaccurate and significantly affect the classification task performance. To address this issue, we first create mask images of the RGB images which are used as input to the Convolutional Neural Network (CNN) for efficient classification of different satellites and debris. The depth images are first de-noised and hole filled using a simple morphological opening operation. Then masked images are calculated using both RGB and processed depth images. This masking operation provides two advantages: 1. it removes noise and fills the holes in the depth images and 2. it highlights satellites and debris while suppressing other information which does not contribute towards the classification task. We use the pre-trained EfficientNet B4 architecture and fine-tuned it with an edition of Global average pooling (GAP) and three dense layers. Our results show that the inclusion of the masking operation significantly improves the overall classification performance, achieving 97.76% accuracy on the validation data.
在这项工作中，我们提出了一种基于定位和掩蔽的卫星和碎片分类技术。利用空间环境知识的航天器识别(SPARK)数据集由120K图像组成，其中RGB图像和相应的深度图像都可用。然而，深度图像存在噪声和不准确性，严重影响分类任务的性能。为了解决这个问题，我们首先创建RGB图像的掩模图像，这些图像用作卷积神经网络(CNN)的输入，用于有效分类不同的卫星和碎片。深度图像首先去噪，并用简单的形态学打开操作填充孔。然后使用RGB和处理过的深度图像计算蒙版图像。这种屏蔽操作提供了两个优点:1。它去除噪声并填充深度图像和2中的空洞。它突出了卫星和碎片，同时压制了对分类任务没有帮助的其他信息。我们使用预先训练的EfficientNet B4架构，并使用Global average pooling (GAP)的一个版本和三个密集层对其进行微调。我们的研究结果表明，掩蔽操作的加入显著提高了整体分类性能，在验证数据上达到了97.76%的准确率。
{"title":"Localizing Features with Masking for Satellite and Debris Classification","authors":"Shubham Chaudhary, Parima Jain, V. Jakhetiya, Sharath Chandra Guntuku, B. Subudhi","doi":"10.1109/ICIPC53495.2021.9620178","DOIUrl":"https://doi.org/10.1109/ICIPC53495.2021.9620178","url":null,"abstract":"In this work, we propose a localization and masking-based satellite and debris classification technique. SPAce-craft Recognition leveraging Knowledge of space environment (SPARK) dataset consists of 120K images where both RGB and corresponding Depth images are available. However, the depth images are noisy and inaccurate and significantly affect the classification task performance. To address this issue, we first create mask images of the RGB images which are used as input to the Convolutional Neural Network (CNN) for efficient classification of different satellites and debris. The depth images are first de-noised and hole filled using a simple morphological opening operation. Then masked images are calculated using both RGB and processed depth images. This masking operation provides two advantages: 1. it removes noise and fills the holes in the depth images and 2. it highlights satellites and debris while suppressing other information which does not contribute towards the classification task. We use the pre-trained EfficientNet B4 architecture and fine-tuned it with an edition of Global average pooling (GAP) and three dense layers. Our results show that the inclusion of the masking operation significantly improves the overall classification performance, achieving 97.76% accuracy on the validation data.","PeriodicalId":246438,"journal":{"name":"2021 IEEE International Conference on Image Processing Challenges (ICIPC)","volume":"69 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121557702","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-09-19DOI: 10.1109/ICIPC53495.2021.9620192
Nouar Aldahoul, H. A. Karim, Mhd Adel Momo
Spacecraft recognition is a significant component of space situational awareness (SSA), especially for applications such as active debris removal, on-orbit servicing, and satellite formation. The complexity of recognition in actual space imagery is caused by a large diversity in sensing conditions, including background noise, low signal-to-noise ratio, different orbital scenarios, and high contrast. This paper addresses the previous problem and proposes multimodal convolutional neural networks (CNNs) for spacecraft detection and classification. The proposed solution includes two models: 1) a pre-trained ResNet50 CNN connected to a support vector machine (SVM) classifier for classification of RGB images. 2) an end-to-end CNN for classification of depth images. The experiments conducted on a novel SPARK dataset was generated under a realistic space simulation environment and has 150k of RGB images and 150k of depth images with 11 categories. The results show high performance of the proposed solution in terms of accuracy (89 %), F1 score (87 %), and Perf metric (1.8).
{"title":"RGB-D Based Multimodal Convolutional Neural Networks for Spacecraft Recognition","authors":"Nouar Aldahoul, H. A. Karim, Mhd Adel Momo","doi":"10.1109/ICIPC53495.2021.9620192","DOIUrl":"https://doi.org/10.1109/ICIPC53495.2021.9620192","url":null,"abstract":"Spacecraft recognition is a significant component of space situational awareness (SSA), especially for applications such as active debris removal, on-orbit servicing, and satellite formation. The complexity of recognition in actual space imagery is caused by a large diversity in sensing conditions, including background noise, low signal-to-noise ratio, different orbital scenarios, and high contrast. This paper addresses the previous problem and proposes multimodal convolutional neural networks (CNNs) for spacecraft detection and classification. The proposed solution includes two models: 1) a pre-trained ResNet50 CNN connected to a support vector machine (SVM) classifier for classification of RGB images. 2) an end-to-end CNN for classification of depth images. The experiments conducted on a novel SPARK dataset was generated under a realistic space simulation environment and has 150k of RGB images and 150k of depth images with 11 categories. The results show high performance of the proposed solution in terms of accuracy (89 %), F1 score (87 %), and Perf metric (1.8).","PeriodicalId":246438,"journal":{"name":"2021 IEEE International Conference on Image Processing Challenges (ICIPC)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127387922","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-09-19DOI: 10.1109/ICIPC53495.2021.9620184
M. A. Musallam, Vincent Gaudillière, Enjie Ghorbel, Kassem Al Ismaeil, M. Perez, Michel Poucet, Djamila Aouada
SPARK represents the first edition of the SPAcecraft Recognition leveraging Knowledge of space environment competition organized by the Interdisciplinary Centre for Security, Reliability and Trust (SnT) in conjunction with the 2021 IEEE International Conference in Image Processing (ICIP 2021). By providing a unique synthetic dataset composed of 150k annotated multi-modal images, SPARK aims at encouraging researchers to develop innovative solutions for space target recognition and detection. This paper introduces the proposed dataset and provides a global analysis of the results obtained for the 17 submissions.
{"title":"Spacecraft Recognition Leveraging Knowledge of Space Environment: Simulator, Dataset, Competition Design and Analysis","authors":"M. A. Musallam, Vincent Gaudillière, Enjie Ghorbel, Kassem Al Ismaeil, M. Perez, Michel Poucet, Djamila Aouada","doi":"10.1109/ICIPC53495.2021.9620184","DOIUrl":"https://doi.org/10.1109/ICIPC53495.2021.9620184","url":null,"abstract":"SPARK represents the first edition of the SPAcecraft Recognition leveraging Knowledge of space environment competition organized by the Interdisciplinary Centre for Security, Reliability and Trust (SnT) in conjunction with the 2021 IEEE International Conference in Image Processing (ICIP 2021). By providing a unique synthetic dataset composed of 150k annotated multi-modal images, SPARK aims at encouraging researchers to develop innovative solutions for space target recognition and detection. This paper introduces the proposed dataset and provides a global analysis of the results obtained for the 17 submissions.","PeriodicalId":246438,"journal":{"name":"2021 IEEE International Conference on Image Processing Challenges (ICIPC)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123137243","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-09-19DOI: 10.1109/ICIPC53495.2021.9620183
I. Lahouli, M. Jarraya, G. Aversano
In this paper, we propose a multi-modal framework to tackle the SPARK Challenge by classifying satellites using RGB and depth images. Our framework is mainly based on Auto-Encoders (AE)s to embed the two modalities in a common latent space in order to exploit redundant and complementary information between the two types of data.
{"title":"Spark Challenge: Multimodal Classifier for Space Target Recognition","authors":"I. Lahouli, M. Jarraya, G. Aversano","doi":"10.1109/ICIPC53495.2021.9620183","DOIUrl":"https://doi.org/10.1109/ICIPC53495.2021.9620183","url":null,"abstract":"In this paper, we propose a multi-modal framework to tackle the SPARK Challenge by classifying satellites using RGB and depth images. Our framework is mainly based on Auto-Encoders (AE)s to embed the two modalities in a common latent space in order to exploit redundant and complementary information between the two types of data.","PeriodicalId":246438,"journal":{"name":"2021 IEEE International Conference on Image Processing Challenges (ICIPC)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121977617","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：